Paper Title: Computational Storage: Leveraging eFPGAs for Application Acceleration

Paper Abstract: Many Computational Storage applications could benefit from programmable logic for accelerating applications and making quick updates. However, standalone FPGAs are often too expensive, take up too much board space, and dissipate too much power. The embedded FPGA (eFPGA) is a beneficial alternative as it can provide programmable logic from 1K to >> 1M LUTS as part of the processing unit in the SoC, thus saving onboard space, power, and cost. New eFPGA design advances also reduce interconnect size and increase utilization, and the latest architectures allow as fast as 10us reconfiguration through a C++ program as well as enabling the processor to do paging with eFPGA designs. The result is greater compute density via integration without degrading system performance or increasing development cost or time.

Paper Author: Ralph Grundler, Sr. Director Technical Marketing, Flex

Author Bio: Ralph Grundler is Senior Director of Marketing and Architecture Solutions at Flex Logix, the leading supplier of eFPGA technology. An experienced business development professional, Ralph has a long history in the development and marketing of semiconductors, IP, SoCs, FPGAs, and embedded systems. Before joining Flex Logix, he worked at Synopsys, where he did marketing for Interface IP subsystems and IP Prototyping Kits as well as business development for the Japanese market. He has done many video and live presentations on a wide variety of technical subjects. He has 30 years of computer and semiconductor industry experience.